Skip to content

[v5] 修复自适应初始化把规则奖励当成奖励模型 - #10495

Open
qychen2001 wants to merge 1 commit into
dev-swift-v5from
fix/v5-bug-1102
Open

qychen2001 wants to merge 1 commit into
dev-swift-v5from
fix/v5-bug-1102

[v5] Register only reward-model scorers for adaptive scaling

7b8b637
Select commit
Loading
Failed to load commit list.